在我們的研究中，首先對原始文章找出與摘要每一句最相關的句子，接著對編碼器使用了對比學習方法使得編碼過後的向量可以獲得與摘要更加相關的原始文章向量使得解碼器產出的摘要更符合事實一致。;Hallucination, also known as factual inconsistency, is when models generate summaries that contain incorrect information or information not mentioned in source text.
It is a critical problem in abstractive summarization and makes summaries generated by models hard to use in practice. Previous works prefer to add additional information such as background knowledge into the model or use post-correct/rank method after decoding to improve this headache.
Contrastive learning is a new model-training method and has achieved excellent results in the Image Processing field. The concept is to use the contrast between positive and negative samples to make vectors learned by the model cluster together. Given the anchor point, the distance between the anchor point and the positive samples will be closer, and the distance between the anchor point and the negative samples will be farther. This way, the model has the ability to distinguish positive examples from negative examples to a certain extent.
We propose a new method to improve factual consistency by separating representation of the most relevant sentences and the least relevant sentences from the source document during the training phase through contrastive learning so that the model can learn how to generate summaries that are more relevant to the main points of the source documents.
